Theoreticallyhugo
commited on
Commit
•
3033175
1
Parent(s):
2dd8aaf
Training in progress, epoch 14, checkpoint
Browse files
checkpoint-1134/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 592318676
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b494b4a1f1e67ab2605723b5a214f4c2b23a4612d8d4cebfb7f418d1fa48caa6
|
3 |
size 592318676
|
checkpoint-1134/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1014645498
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96f8cd1b63c2a9106663a7ae03752892aedf4ae6836b94a712e855a66ae0b8f5
|
3 |
size 1014645498
|
checkpoint-1134/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf01be357caf0448dba368f5fc5a45f534a0919f6ea3b798ae4caf1706d7e9ae
|
3 |
size 14244
|
checkpoint-1134/trainer_state.json
CHANGED
@@ -11,560 +11,560 @@
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
-
"f1-score": 0.
|
15 |
-
"precision": 0.
|
16 |
-
"recall": 0.
|
17 |
-
"support":
|
18 |
},
|
19 |
"eval_I": {
|
20 |
-
"f1-score": 0.
|
21 |
-
"precision": 0.
|
22 |
-
"recall": 0.
|
23 |
-
"support":
|
24 |
},
|
25 |
"eval_O": {
|
26 |
-
"f1-score": 0.
|
27 |
-
"precision": 0.
|
28 |
-
"recall": 0.
|
29 |
-
"support":
|
30 |
},
|
31 |
-
"eval_accuracy": 0.
|
32 |
-
"eval_loss": 0.
|
33 |
"eval_macro avg": {
|
34 |
-
"f1-score": 0.
|
35 |
-
"precision": 0.
|
36 |
-
"recall": 0.
|
37 |
-
"support":
|
38 |
-
},
|
39 |
-
"eval_runtime": 4.
|
40 |
-
"eval_samples_per_second": 17.
|
41 |
-
"eval_steps_per_second": 2.
|
42 |
"eval_weighted avg": {
|
43 |
-
"f1-score": 0.
|
44 |
-
"precision": 0.
|
45 |
-
"recall": 0.
|
46 |
-
"support":
|
47 |
},
|
48 |
"step": 81
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
-
"f1-score": 0.
|
54 |
-
"precision": 0.
|
55 |
-
"recall": 0.
|
56 |
-
"support":
|
57 |
},
|
58 |
"eval_I": {
|
59 |
-
"f1-score": 0.
|
60 |
-
"precision": 0.
|
61 |
-
"recall": 0.
|
62 |
-
"support":
|
63 |
},
|
64 |
"eval_O": {
|
65 |
-
"f1-score": 0.
|
66 |
-
"precision": 0.
|
67 |
-
"recall": 0.
|
68 |
-
"support":
|
69 |
},
|
70 |
-
"eval_accuracy": 0.
|
71 |
-
"eval_loss": 0.
|
72 |
"eval_macro avg": {
|
73 |
-
"f1-score": 0.
|
74 |
-
"precision": 0.
|
75 |
-
"recall": 0.
|
76 |
-
"support":
|
77 |
-
},
|
78 |
-
"eval_runtime": 4.
|
79 |
-
"eval_samples_per_second": 17.
|
80 |
-
"eval_steps_per_second": 2.
|
81 |
"eval_weighted avg": {
|
82 |
-
"f1-score": 0.
|
83 |
-
"precision": 0.
|
84 |
-
"recall": 0.
|
85 |
-
"support":
|
86 |
},
|
87 |
"step": 162
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
-
"f1-score": 0.
|
93 |
-
"precision": 0.
|
94 |
-
"recall": 0.
|
95 |
-
"support":
|
96 |
},
|
97 |
"eval_I": {
|
98 |
-
"f1-score": 0.
|
99 |
-
"precision": 0.
|
100 |
-
"recall": 0.
|
101 |
-
"support":
|
102 |
},
|
103 |
"eval_O": {
|
104 |
-
"f1-score": 0.
|
105 |
-
"precision": 0.
|
106 |
-
"recall": 0.
|
107 |
-
"support":
|
108 |
},
|
109 |
-
"eval_accuracy": 0.
|
110 |
-
"eval_loss": 0.
|
111 |
"eval_macro avg": {
|
112 |
-
"f1-score": 0.
|
113 |
-
"precision": 0.
|
114 |
-
"recall": 0.
|
115 |
-
"support":
|
116 |
-
},
|
117 |
-
"eval_runtime": 4.
|
118 |
-
"eval_samples_per_second": 17.
|
119 |
-
"eval_steps_per_second": 2.
|
120 |
"eval_weighted avg": {
|
121 |
-
"f1-score": 0.
|
122 |
-
"precision": 0.
|
123 |
-
"recall": 0.
|
124 |
-
"support":
|
125 |
},
|
126 |
"step": 243
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
-
"f1-score": 0.
|
132 |
-
"precision": 0.
|
133 |
-
"recall": 0.
|
134 |
-
"support":
|
135 |
},
|
136 |
"eval_I": {
|
137 |
-
"f1-score": 0.
|
138 |
-
"precision": 0.
|
139 |
-
"recall": 0.
|
140 |
-
"support":
|
141 |
},
|
142 |
"eval_O": {
|
143 |
-
"f1-score": 0.
|
144 |
-
"precision": 0.
|
145 |
-
"recall": 0.
|
146 |
-
"support":
|
147 |
},
|
148 |
-
"eval_accuracy": 0.
|
149 |
-
"eval_loss": 0.
|
150 |
"eval_macro avg": {
|
151 |
-
"f1-score": 0.
|
152 |
-
"precision": 0.
|
153 |
-
"recall": 0.
|
154 |
-
"support":
|
155 |
-
},
|
156 |
-
"eval_runtime": 4.
|
157 |
-
"eval_samples_per_second": 17.
|
158 |
-
"eval_steps_per_second": 2.
|
159 |
"eval_weighted avg": {
|
160 |
-
"f1-score": 0.
|
161 |
-
"precision": 0.
|
162 |
-
"recall": 0.
|
163 |
-
"support":
|
164 |
},
|
165 |
"step": 324
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
-
"f1-score": 0.
|
171 |
-
"precision": 0.
|
172 |
-
"recall": 0.
|
173 |
-
"support":
|
174 |
},
|
175 |
"eval_I": {
|
176 |
-
"f1-score": 0.
|
177 |
-
"precision": 0.
|
178 |
-
"recall": 0.
|
179 |
-
"support":
|
180 |
},
|
181 |
"eval_O": {
|
182 |
-
"f1-score": 0.
|
183 |
-
"precision": 0.
|
184 |
-
"recall": 0.
|
185 |
-
"support":
|
186 |
},
|
187 |
-
"eval_accuracy": 0.
|
188 |
-
"eval_loss": 0.
|
189 |
"eval_macro avg": {
|
190 |
-
"f1-score": 0.
|
191 |
-
"precision": 0.
|
192 |
-
"recall": 0.
|
193 |
-
"support":
|
194 |
-
},
|
195 |
-
"eval_runtime": 4.
|
196 |
-
"eval_samples_per_second":
|
197 |
-
"eval_steps_per_second": 2.
|
198 |
"eval_weighted avg": {
|
199 |
-
"f1-score": 0.
|
200 |
-
"precision": 0.
|
201 |
-
"recall": 0.
|
202 |
-
"support":
|
203 |
},
|
204 |
"step": 405
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
-
"f1-score": 0.
|
210 |
-
"precision": 0.
|
211 |
-
"recall": 0.
|
212 |
-
"support":
|
213 |
},
|
214 |
"eval_I": {
|
215 |
-
"f1-score": 0.
|
216 |
-
"precision": 0.
|
217 |
-
"recall": 0.
|
218 |
-
"support":
|
219 |
},
|
220 |
"eval_O": {
|
221 |
-
"f1-score": 0.
|
222 |
-
"precision": 0.
|
223 |
-
"recall": 0.
|
224 |
-
"support":
|
225 |
},
|
226 |
-
"eval_accuracy": 0.
|
227 |
-
"eval_loss": 0.
|
228 |
"eval_macro avg": {
|
229 |
-
"f1-score": 0.
|
230 |
-
"precision": 0.
|
231 |
-
"recall": 0.
|
232 |
-
"support":
|
233 |
-
},
|
234 |
-
"eval_runtime": 4.
|
235 |
-
"eval_samples_per_second":
|
236 |
-
"eval_steps_per_second": 2.
|
237 |
"eval_weighted avg": {
|
238 |
-
"f1-score": 0.
|
239 |
-
"precision": 0.
|
240 |
-
"recall": 0.
|
241 |
-
"support":
|
242 |
},
|
243 |
"step": 486
|
244 |
},
|
245 |
{
|
246 |
"epoch": 6.17,
|
247 |
-
"grad_norm":
|
248 |
"learning_rate": 1.7530864197530865e-05,
|
249 |
-
"loss": 0.
|
250 |
"step": 500
|
251 |
},
|
252 |
{
|
253 |
"epoch": 7.0,
|
254 |
"eval_B": {
|
255 |
-
"f1-score": 0.
|
256 |
-
"precision": 0.
|
257 |
-
"recall": 0.
|
258 |
-
"support":
|
259 |
},
|
260 |
"eval_I": {
|
261 |
-
"f1-score": 0.
|
262 |
-
"precision": 0.
|
263 |
-
"recall": 0.
|
264 |
-
"support":
|
265 |
},
|
266 |
"eval_O": {
|
267 |
-
"f1-score": 0.
|
268 |
-
"precision": 0.
|
269 |
-
"recall": 0.
|
270 |
-
"support":
|
271 |
},
|
272 |
-
"eval_accuracy": 0.
|
273 |
-
"eval_loss": 0.
|
274 |
"eval_macro avg": {
|
275 |
-
"f1-score": 0.
|
276 |
-
"precision": 0.
|
277 |
-
"recall": 0.
|
278 |
-
"support":
|
279 |
-
},
|
280 |
-
"eval_runtime": 4.
|
281 |
-
"eval_samples_per_second":
|
282 |
-
"eval_steps_per_second": 2.
|
283 |
"eval_weighted avg": {
|
284 |
-
"f1-score": 0.
|
285 |
-
"precision": 0.
|
286 |
-
"recall": 0.
|
287 |
-
"support":
|
288 |
},
|
289 |
"step": 567
|
290 |
},
|
291 |
{
|
292 |
"epoch": 8.0,
|
293 |
"eval_B": {
|
294 |
-
"f1-score": 0.
|
295 |
-
"precision": 0.
|
296 |
-
"recall": 0.
|
297 |
-
"support":
|
298 |
},
|
299 |
"eval_I": {
|
300 |
-
"f1-score": 0.
|
301 |
-
"precision": 0.
|
302 |
-
"recall": 0.
|
303 |
-
"support":
|
304 |
},
|
305 |
"eval_O": {
|
306 |
-
"f1-score": 0.
|
307 |
-
"precision": 0.
|
308 |
-
"recall": 0.
|
309 |
-
"support":
|
310 |
},
|
311 |
-
"eval_accuracy": 0.
|
312 |
-
"eval_loss": 0.
|
313 |
"eval_macro avg": {
|
314 |
-
"f1-score": 0.
|
315 |
-
"precision": 0.
|
316 |
-
"recall": 0.
|
317 |
-
"support":
|
318 |
-
},
|
319 |
-
"eval_runtime": 4.
|
320 |
-
"eval_samples_per_second":
|
321 |
-
"eval_steps_per_second": 2.
|
322 |
"eval_weighted avg": {
|
323 |
-
"f1-score": 0.
|
324 |
-
"precision": 0.
|
325 |
-
"recall": 0.
|
326 |
-
"support":
|
327 |
},
|
328 |
"step": 648
|
329 |
},
|
330 |
{
|
331 |
"epoch": 9.0,
|
332 |
"eval_B": {
|
333 |
-
"f1-score": 0.
|
334 |
-
"precision": 0.
|
335 |
-
"recall": 0.
|
336 |
-
"support":
|
337 |
},
|
338 |
"eval_I": {
|
339 |
-
"f1-score": 0.
|
340 |
-
"precision": 0.
|
341 |
-
"recall": 0.
|
342 |
-
"support":
|
343 |
},
|
344 |
"eval_O": {
|
345 |
-
"f1-score": 0.
|
346 |
-
"precision": 0.
|
347 |
-
"recall": 0.
|
348 |
-
"support":
|
349 |
},
|
350 |
-
"eval_accuracy": 0.
|
351 |
-
"eval_loss": 0.
|
352 |
"eval_macro avg": {
|
353 |
-
"f1-score": 0.
|
354 |
-
"precision": 0.
|
355 |
-
"recall": 0.
|
356 |
-
"support":
|
357 |
-
},
|
358 |
-
"eval_runtime": 4.
|
359 |
-
"eval_samples_per_second": 17.
|
360 |
-
"eval_steps_per_second": 2.
|
361 |
"eval_weighted avg": {
|
362 |
-
"f1-score": 0.
|
363 |
-
"precision": 0.
|
364 |
-
"recall": 0.
|
365 |
-
"support":
|
366 |
},
|
367 |
"step": 729
|
368 |
},
|
369 |
{
|
370 |
"epoch": 10.0,
|
371 |
"eval_B": {
|
372 |
-
"f1-score": 0.
|
373 |
-
"precision": 0.
|
374 |
-
"recall": 0.
|
375 |
-
"support":
|
376 |
},
|
377 |
"eval_I": {
|
378 |
-
"f1-score": 0.
|
379 |
-
"precision": 0.
|
380 |
-
"recall": 0.
|
381 |
-
"support":
|
382 |
},
|
383 |
"eval_O": {
|
384 |
-
"f1-score": 0.
|
385 |
-
"precision": 0.
|
386 |
-
"recall": 0.
|
387 |
-
"support":
|
388 |
},
|
389 |
-
"eval_accuracy": 0.
|
390 |
-
"eval_loss": 0.
|
391 |
"eval_macro avg": {
|
392 |
-
"f1-score": 0.
|
393 |
-
"precision": 0.
|
394 |
-
"recall": 0.
|
395 |
-
"support":
|
396 |
-
},
|
397 |
-
"eval_runtime": 4.
|
398 |
-
"eval_samples_per_second": 17.
|
399 |
-
"eval_steps_per_second": 2.
|
400 |
"eval_weighted avg": {
|
401 |
-
"f1-score": 0.
|
402 |
-
"precision": 0.
|
403 |
-
"recall": 0.
|
404 |
-
"support":
|
405 |
},
|
406 |
"step": 810
|
407 |
},
|
408 |
{
|
409 |
"epoch": 11.0,
|
410 |
"eval_B": {
|
411 |
-
"f1-score": 0.
|
412 |
-
"precision": 0.
|
413 |
-
"recall": 0.
|
414 |
-
"support":
|
415 |
},
|
416 |
"eval_I": {
|
417 |
-
"f1-score": 0.
|
418 |
-
"precision": 0.
|
419 |
-
"recall": 0.
|
420 |
-
"support":
|
421 |
},
|
422 |
"eval_O": {
|
423 |
-
"f1-score": 0.
|
424 |
-
"precision": 0.
|
425 |
-
"recall": 0.
|
426 |
-
"support":
|
427 |
},
|
428 |
-
"eval_accuracy": 0.
|
429 |
-
"eval_loss": 0.
|
430 |
"eval_macro avg": {
|
431 |
-
"f1-score": 0.
|
432 |
-
"precision": 0.
|
433 |
-
"recall": 0.
|
434 |
-
"support":
|
435 |
-
},
|
436 |
-
"eval_runtime": 4.
|
437 |
-
"eval_samples_per_second": 17.
|
438 |
-
"eval_steps_per_second": 2.
|
439 |
"eval_weighted avg": {
|
440 |
-
"f1-score": 0.
|
441 |
-
"precision": 0.
|
442 |
-
"recall": 0.
|
443 |
-
"support":
|
444 |
},
|
445 |
"step": 891
|
446 |
},
|
447 |
{
|
448 |
"epoch": 12.0,
|
449 |
"eval_B": {
|
450 |
-
"f1-score": 0.
|
451 |
-
"precision": 0.
|
452 |
-
"recall": 0.
|
453 |
-
"support":
|
454 |
},
|
455 |
"eval_I": {
|
456 |
-
"f1-score": 0.
|
457 |
-
"precision": 0.
|
458 |
-
"recall": 0.
|
459 |
-
"support":
|
460 |
},
|
461 |
"eval_O": {
|
462 |
-
"f1-score": 0.
|
463 |
-
"precision": 0.
|
464 |
-
"recall": 0.
|
465 |
-
"support":
|
466 |
},
|
467 |
-
"eval_accuracy": 0.
|
468 |
-
"eval_loss": 0.
|
469 |
"eval_macro avg": {
|
470 |
-
"f1-score": 0.
|
471 |
-
"precision": 0.
|
472 |
-
"recall": 0.
|
473 |
-
"support":
|
474 |
-
},
|
475 |
-
"eval_runtime": 4.
|
476 |
-
"eval_samples_per_second": 17.
|
477 |
-
"eval_steps_per_second": 2.
|
478 |
"eval_weighted avg": {
|
479 |
-
"f1-score": 0.
|
480 |
-
"precision": 0.
|
481 |
-
"recall": 0.
|
482 |
-
"support":
|
483 |
},
|
484 |
"step": 972
|
485 |
},
|
486 |
{
|
487 |
"epoch": 12.35,
|
488 |
-
"grad_norm": 0.
|
489 |
"learning_rate": 1.506172839506173e-05,
|
490 |
-
"loss": 0.
|
491 |
"step": 1000
|
492 |
},
|
493 |
{
|
494 |
"epoch": 13.0,
|
495 |
"eval_B": {
|
496 |
-
"f1-score": 0.
|
497 |
-
"precision": 0.
|
498 |
-
"recall": 0.
|
499 |
-
"support":
|
500 |
},
|
501 |
"eval_I": {
|
502 |
-
"f1-score": 0.
|
503 |
-
"precision": 0.
|
504 |
-
"recall": 0.
|
505 |
-
"support":
|
506 |
},
|
507 |
"eval_O": {
|
508 |
-
"f1-score": 0.
|
509 |
-
"precision": 0.
|
510 |
-
"recall": 0.
|
511 |
-
"support":
|
512 |
},
|
513 |
-
"eval_accuracy": 0.
|
514 |
-
"eval_loss": 0.
|
515 |
"eval_macro avg": {
|
516 |
-
"f1-score": 0.
|
517 |
-
"precision": 0.
|
518 |
-
"recall": 0.
|
519 |
-
"support":
|
520 |
-
},
|
521 |
-
"eval_runtime": 4.
|
522 |
-
"eval_samples_per_second": 17.
|
523 |
-
"eval_steps_per_second": 2.
|
524 |
"eval_weighted avg": {
|
525 |
-
"f1-score": 0.
|
526 |
-
"precision": 0.
|
527 |
-
"recall": 0.
|
528 |
-
"support":
|
529 |
},
|
530 |
"step": 1053
|
531 |
},
|
532 |
{
|
533 |
"epoch": 14.0,
|
534 |
"eval_B": {
|
535 |
-
"f1-score": 0.
|
536 |
-
"precision": 0.
|
537 |
-
"recall": 0.
|
538 |
-
"support":
|
539 |
},
|
540 |
"eval_I": {
|
541 |
-
"f1-score": 0.
|
542 |
-
"precision": 0.
|
543 |
-
"recall": 0.
|
544 |
-
"support":
|
545 |
},
|
546 |
"eval_O": {
|
547 |
-
"f1-score": 0.
|
548 |
-
"precision": 0.
|
549 |
-
"recall": 0.
|
550 |
-
"support":
|
551 |
},
|
552 |
-
"eval_accuracy": 0.
|
553 |
-
"eval_loss": 0.
|
554 |
"eval_macro avg": {
|
555 |
-
"f1-score": 0.
|
556 |
-
"precision": 0.
|
557 |
-
"recall": 0.
|
558 |
-
"support":
|
559 |
-
},
|
560 |
-
"eval_runtime": 4.
|
561 |
-
"eval_samples_per_second": 17.
|
562 |
-
"eval_steps_per_second": 2.
|
563 |
"eval_weighted avg": {
|
564 |
-
"f1-score": 0.
|
565 |
-
"precision": 0.
|
566 |
-
"recall": 0.
|
567 |
-
"support":
|
568 |
},
|
569 |
"step": 1134
|
570 |
}
|
@@ -574,7 +574,7 @@
|
|
574 |
"num_input_tokens_seen": 0,
|
575 |
"num_train_epochs": 50,
|
576 |
"save_steps": 500,
|
577 |
-
"total_flos":
|
578 |
"train_batch_size": 4,
|
579 |
"trial_name": null,
|
580 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
"eval_B": {
|
14 |
+
"f1-score": 0.7905866302864938,
|
15 |
+
"precision": 0.7768096514745308,
|
16 |
+
"recall": 0.8048611111111111,
|
17 |
+
"support": 1440.0
|
18 |
},
|
19 |
"eval_I": {
|
20 |
+
"f1-score": 0.9005331227169513,
|
21 |
+
"precision": 0.9637593111099372,
|
22 |
+
"recall": 0.8450919534905267,
|
23 |
+
"support": 21587.0
|
24 |
},
|
25 |
"eval_O": {
|
26 |
+
"f1-score": 0.8288892663043479,
|
27 |
+
"precision": 0.7463108800367001,
|
28 |
+
"recall": 0.9320156593144275,
|
29 |
+
"support": 10473.0
|
30 |
},
|
31 |
+
"eval_accuracy": 0.8705373134328358,
|
32 |
+
"eval_loss": 0.32930415868759155,
|
33 |
"eval_macro avg": {
|
34 |
+
"f1-score": 0.8400030064359308,
|
35 |
+
"precision": 0.8289599475403894,
|
36 |
+
"recall": 0.8606562413053552,
|
37 |
+
"support": 33500.0
|
38 |
+
},
|
39 |
+
"eval_runtime": 4.7349,
|
40 |
+
"eval_samples_per_second": 17.107,
|
41 |
+
"eval_steps_per_second": 2.323,
|
42 |
"eval_weighted avg": {
|
43 |
+
"f1-score": 0.8734092702599646,
|
44 |
+
"precision": 0.8877430445874,
|
45 |
+
"recall": 0.8705373134328358,
|
46 |
+
"support": 33500.0
|
47 |
},
|
48 |
"step": 81
|
49 |
},
|
50 |
{
|
51 |
"epoch": 2.0,
|
52 |
"eval_B": {
|
53 |
+
"f1-score": 0.8656218739579861,
|
54 |
+
"precision": 0.8325849903784477,
|
55 |
+
"recall": 0.9013888888888889,
|
56 |
+
"support": 1440.0
|
57 |
},
|
58 |
"eval_I": {
|
59 |
+
"f1-score": 0.9547168948727912,
|
60 |
+
"precision": 0.9423736462093862,
|
61 |
+
"recall": 0.9673877796822161,
|
62 |
+
"support": 21587.0
|
63 |
},
|
64 |
"eval_O": {
|
65 |
+
"f1-score": 0.9013528191962081,
|
66 |
+
"precision": 0.9332379102341274,
|
67 |
+
"recall": 0.8715745249689678,
|
68 |
+
"support": 10473.0
|
69 |
},
|
70 |
+
"eval_accuracy": 0.9345970149253732,
|
71 |
+
"eval_loss": 0.2162298709154129,
|
72 |
"eval_macro avg": {
|
73 |
+
"f1-score": 0.9072305293423284,
|
74 |
+
"precision": 0.902732182273987,
|
75 |
+
"recall": 0.9134503978466909,
|
76 |
+
"support": 33500.0
|
77 |
+
},
|
78 |
+
"eval_runtime": 4.753,
|
79 |
+
"eval_samples_per_second": 17.042,
|
80 |
+
"eval_steps_per_second": 2.314,
|
81 |
"eval_weighted avg": {
|
82 |
+
"f1-score": 0.9342040950316517,
|
83 |
+
"precision": 0.9347982961417612,
|
84 |
+
"recall": 0.9345970149253732,
|
85 |
+
"support": 33500.0
|
86 |
},
|
87 |
"step": 162
|
88 |
},
|
89 |
{
|
90 |
"epoch": 3.0,
|
91 |
"eval_B": {
|
92 |
+
"f1-score": 0.8603587759409076,
|
93 |
+
"precision": 0.8717034925160371,
|
94 |
+
"recall": 0.8493055555555555,
|
95 |
+
"support": 1440.0
|
96 |
},
|
97 |
"eval_I": {
|
98 |
+
"f1-score": 0.9434195218082959,
|
99 |
+
"precision": 0.9677057963955188,
|
100 |
+
"recall": 0.9203224162690509,
|
101 |
+
"support": 21587.0
|
102 |
},
|
103 |
"eval_O": {
|
104 |
+
"f1-score": 0.8879310344827586,
|
105 |
+
"precision": 0.8459410391631365,
|
106 |
+
"recall": 0.9343072663038289,
|
107 |
+
"support": 10473.0
|
108 |
},
|
109 |
+
"eval_accuracy": 0.9216417910447762,
|
110 |
+
"eval_loss": 0.24082203209400177,
|
111 |
"eval_macro avg": {
|
112 |
+
"f1-score": 0.8972364440773206,
|
113 |
+
"precision": 0.8951167760248975,
|
114 |
+
"recall": 0.9013117460428117,
|
115 |
+
"support": 33500.0
|
116 |
+
},
|
117 |
+
"eval_runtime": 4.7554,
|
118 |
+
"eval_samples_per_second": 17.033,
|
119 |
+
"eval_steps_per_second": 2.313,
|
120 |
"eval_weighted avg": {
|
121 |
+
"f1-score": 0.9225019575751797,
|
122 |
+
"precision": 0.9255121957960801,
|
123 |
+
"recall": 0.9216417910447762,
|
124 |
+
"support": 33500.0
|
125 |
},
|
126 |
"step": 243
|
127 |
},
|
128 |
{
|
129 |
"epoch": 4.0,
|
130 |
"eval_B": {
|
131 |
+
"f1-score": 0.8804020100502512,
|
132 |
+
"precision": 0.8504854368932039,
|
133 |
+
"recall": 0.9125,
|
134 |
+
"support": 1440.0
|
135 |
},
|
136 |
"eval_I": {
|
137 |
+
"f1-score": 0.9589184992350025,
|
138 |
+
"precision": 0.945595388218339,
|
139 |
+
"recall": 0.9726224116366332,
|
140 |
+
"support": 21587.0
|
141 |
},
|
142 |
"eval_O": {
|
143 |
+
"f1-score": 0.9091178797468354,
|
144 |
+
"precision": 0.9427750999897446,
|
145 |
+
"recall": 0.877780960565263,
|
146 |
+
"support": 10473.0
|
147 |
},
|
148 |
+
"eval_accuracy": 0.9403880597014925,
|
149 |
+
"eval_loss": 0.22083505988121033,
|
150 |
"eval_macro avg": {
|
151 |
+
"f1-score": 0.9161461296773631,
|
152 |
+
"precision": 0.9129519750337626,
|
153 |
+
"recall": 0.9209677907339654,
|
154 |
+
"support": 33500.0
|
155 |
+
},
|
156 |
+
"eval_runtime": 4.7449,
|
157 |
+
"eval_samples_per_second": 17.071,
|
158 |
+
"eval_steps_per_second": 2.318,
|
159 |
"eval_weighted avg": {
|
160 |
+
"f1-score": 0.9399744505088647,
|
161 |
+
"precision": 0.9406253819936745,
|
162 |
+
"recall": 0.9403880597014925,
|
163 |
+
"support": 33500.0
|
164 |
},
|
165 |
"step": 324
|
166 |
},
|
167 |
{
|
168 |
"epoch": 5.0,
|
169 |
"eval_B": {
|
170 |
+
"f1-score": 0.8879781420765027,
|
171 |
+
"precision": 0.8736559139784946,
|
172 |
+
"recall": 0.9027777777777778,
|
173 |
+
"support": 1440.0
|
174 |
},
|
175 |
"eval_I": {
|
176 |
+
"f1-score": 0.9613201259451634,
|
177 |
+
"precision": 0.9539317642765919,
|
178 |
+
"recall": 0.9688238291564367,
|
179 |
+
"support": 21587.0
|
180 |
},
|
181 |
"eval_O": {
|
182 |
+
"f1-score": 0.916006030835076,
|
183 |
+
"precision": 0.9334853291038858,
|
184 |
+
"recall": 0.899169292466342,
|
185 |
+
"support": 10473.0
|
186 |
},
|
187 |
+
"eval_accuracy": 0.9442089552238806,
|
188 |
+
"eval_loss": 0.2257838249206543,
|
189 |
"eval_macro avg": {
|
190 |
+
"f1-score": 0.921768099618914,
|
191 |
+
"precision": 0.9203576691196576,
|
192 |
+
"recall": 0.9235902998001855,
|
193 |
+
"support": 33500.0
|
194 |
+
},
|
195 |
+
"eval_runtime": 4.7845,
|
196 |
+
"eval_samples_per_second": 16.93,
|
197 |
+
"eval_steps_per_second": 2.299,
|
198 |
"eval_weighted avg": {
|
199 |
+
"f1-score": 0.9440011117702735,
|
200 |
+
"precision": 0.9440889959185916,
|
201 |
+
"recall": 0.9442089552238806,
|
202 |
+
"support": 33500.0
|
203 |
},
|
204 |
"step": 405
|
205 |
},
|
206 |
{
|
207 |
"epoch": 6.0,
|
208 |
"eval_B": {
|
209 |
+
"f1-score": 0.8873579056148813,
|
210 |
+
"precision": 0.8803827751196173,
|
211 |
+
"recall": 0.8944444444444445,
|
212 |
+
"support": 1440.0
|
213 |
},
|
214 |
"eval_I": {
|
215 |
+
"f1-score": 0.9622060984570168,
|
216 |
+
"precision": 0.9539267015706806,
|
217 |
+
"recall": 0.9706304720433594,
|
218 |
+
"support": 21587.0
|
219 |
},
|
220 |
"eval_O": {
|
221 |
+
"f1-score": 0.9182769530299342,
|
222 |
+
"precision": 0.9365567911040509,
|
223 |
+
"recall": 0.9006970304592762,
|
224 |
+
"support": 10473.0
|
225 |
},
|
226 |
+
"eval_accuracy": 0.9454925373134329,
|
227 |
+
"eval_loss": 0.2242102175951004,
|
228 |
"eval_macro avg": {
|
229 |
+
"f1-score": 0.9226136523672773,
|
230 |
+
"precision": 0.923622089264783,
|
231 |
+
"recall": 0.9219239823156933,
|
232 |
+
"support": 33500.0
|
233 |
+
},
|
234 |
+
"eval_runtime": 4.7715,
|
235 |
+
"eval_samples_per_second": 16.976,
|
236 |
+
"eval_steps_per_second": 2.305,
|
237 |
"eval_weighted avg": {
|
238 |
+
"f1-score": 0.945255312255509,
|
239 |
+
"precision": 0.9453351097376493,
|
240 |
+
"recall": 0.9454925373134329,
|
241 |
+
"support": 33500.0
|
242 |
},
|
243 |
"step": 486
|
244 |
},
|
245 |
{
|
246 |
"epoch": 6.17,
|
247 |
+
"grad_norm": 1.8705081939697266,
|
248 |
"learning_rate": 1.7530864197530865e-05,
|
249 |
+
"loss": 0.1601,
|
250 |
"step": 500
|
251 |
},
|
252 |
{
|
253 |
"epoch": 7.0,
|
254 |
"eval_B": {
|
255 |
+
"f1-score": 0.8876749743939911,
|
256 |
+
"precision": 0.8730691739422431,
|
257 |
+
"recall": 0.9027777777777778,
|
258 |
+
"support": 1440.0
|
259 |
},
|
260 |
"eval_I": {
|
261 |
+
"f1-score": 0.9611415113943341,
|
262 |
+
"precision": 0.9581108451482232,
|
263 |
+
"recall": 0.9641914114976606,
|
264 |
+
"support": 21587.0
|
265 |
},
|
266 |
"eval_O": {
|
267 |
+
"f1-score": 0.9164739884393064,
|
268 |
+
"precision": 0.9247594050743657,
|
269 |
+
"recall": 0.9083357204239473,
|
270 |
+
"support": 10473.0
|
271 |
},
|
272 |
+
"eval_accuracy": 0.944089552238806,
|
273 |
+
"eval_loss": 0.22517083585262299,
|
274 |
"eval_macro avg": {
|
275 |
+
"f1-score": 0.9217634914092105,
|
276 |
+
"precision": 0.9186464747216107,
|
277 |
+
"recall": 0.9251016365664619,
|
278 |
+
"support": 33500.0
|
279 |
+
},
|
280 |
+
"eval_runtime": 4.7926,
|
281 |
+
"eval_samples_per_second": 16.901,
|
282 |
+
"eval_steps_per_second": 2.295,
|
283 |
"eval_weighted avg": {
|
284 |
+
"f1-score": 0.9440192791200506,
|
285 |
+
"precision": 0.9440287663891153,
|
286 |
+
"recall": 0.944089552238806,
|
287 |
+
"support": 33500.0
|
288 |
},
|
289 |
"step": 567
|
290 |
},
|
291 |
{
|
292 |
"epoch": 8.0,
|
293 |
"eval_B": {
|
294 |
+
"f1-score": 0.894540522210919,
|
295 |
+
"precision": 0.8740888005301524,
|
296 |
+
"recall": 0.9159722222222222,
|
297 |
+
"support": 1440.0
|
298 |
},
|
299 |
"eval_I": {
|
300 |
+
"f1-score": 0.9638018385639943,
|
301 |
+
"precision": 0.9540255968049378,
|
302 |
+
"recall": 0.9737805160513272,
|
303 |
+
"support": 21587.0
|
304 |
},
|
305 |
"eval_O": {
|
306 |
+
"f1-score": 0.9203132648066569,
|
307 |
+
"precision": 0.9441598875163202,
|
308 |
+
"recall": 0.8976415544734078,
|
309 |
+
"support": 10473.0
|
310 |
},
|
311 |
+
"eval_accuracy": 0.9474925373134329,
|
312 |
+
"eval_loss": 0.24869142472743988,
|
313 |
"eval_macro avg": {
|
314 |
+
"f1-score": 0.9262185418605234,
|
315 |
+
"precision": 0.9240914282838034,
|
316 |
+
"recall": 0.9291314309156524,
|
317 |
+
"support": 33500.0
|
318 |
+
},
|
319 |
+
"eval_runtime": 4.7743,
|
320 |
+
"eval_samples_per_second": 16.966,
|
321 |
+
"eval_steps_per_second": 2.304,
|
322 |
"eval_weighted avg": {
|
323 |
+
"f1-score": 0.947228939205516,
|
324 |
+
"precision": 0.9475052218791054,
|
325 |
+
"recall": 0.9474925373134329,
|
326 |
+
"support": 33500.0
|
327 |
},
|
328 |
"step": 648
|
329 |
},
|
330 |
{
|
331 |
"epoch": 9.0,
|
332 |
"eval_B": {
|
333 |
+
"f1-score": 0.8851236868858015,
|
334 |
+
"precision": 0.8643282594308405,
|
335 |
+
"recall": 0.9069444444444444,
|
336 |
+
"support": 1440.0
|
337 |
},
|
338 |
"eval_I": {
|
339 |
+
"f1-score": 0.9617001723147618,
|
340 |
+
"precision": 0.9540067462849849,
|
341 |
+
"recall": 0.9695186918052532,
|
342 |
+
"support": 21587.0
|
343 |
},
|
344 |
"eval_O": {
|
345 |
+
"f1-score": 0.9165854609237966,
|
346 |
+
"precision": 0.9358272808675754,
|
347 |
+
"recall": 0.8981189725961998,
|
348 |
+
"support": 10473.0
|
349 |
},
|
350 |
+
"eval_accuracy": 0.9445074626865672,
|
351 |
+
"eval_loss": 0.3045330345630646,
|
352 |
"eval_macro avg": {
|
353 |
+
"f1-score": 0.9211364400414532,
|
354 |
+
"precision": 0.9180540955278002,
|
355 |
+
"recall": 0.9248607029486324,
|
356 |
+
"support": 33500.0
|
357 |
+
},
|
358 |
+
"eval_runtime": 4.7599,
|
359 |
+
"eval_samples_per_second": 17.017,
|
360 |
+
"eval_steps_per_second": 2.311,
|
361 |
"eval_weighted avg": {
|
362 |
+
"f1-score": 0.9443044555560967,
|
363 |
+
"precision": 0.9444685205421044,
|
364 |
+
"recall": 0.9445074626865672,
|
365 |
+
"support": 33500.0
|
366 |
},
|
367 |
"step": 729
|
368 |
},
|
369 |
{
|
370 |
"epoch": 10.0,
|
371 |
"eval_B": {
|
372 |
+
"f1-score": 0.8815068493150685,
|
373 |
+
"precision": 0.8695945945945946,
|
374 |
+
"recall": 0.89375,
|
375 |
+
"support": 1440.0
|
376 |
},
|
377 |
"eval_I": {
|
378 |
+
"f1-score": 0.956297959947595,
|
379 |
+
"precision": 0.9660159757999717,
|
380 |
+
"recall": 0.9467735211006625,
|
381 |
+
"support": 21587.0
|
382 |
},
|
383 |
"eval_O": {
|
384 |
+
"f1-score": 0.9101049868766404,
|
385 |
+
"precision": 0.8937678357728068,
|
386 |
+
"recall": 0.9270505108373914,
|
387 |
+
"support": 10473.0
|
388 |
},
|
389 |
+
"eval_accuracy": 0.9383283582089552,
|
390 |
+
"eval_loss": 0.32627996802330017,
|
391 |
"eval_macro avg": {
|
392 |
+
"f1-score": 0.9159699320464346,
|
393 |
+
"precision": 0.909792802055791,
|
394 |
+
"recall": 0.9225246773126846,
|
395 |
+
"support": 33500.0
|
396 |
+
},
|
397 |
+
"eval_runtime": 4.7534,
|
398 |
+
"eval_samples_per_second": 17.04,
|
399 |
+
"eval_steps_per_second": 2.314,
|
400 |
"eval_weighted avg": {
|
401 |
+
"f1-score": 0.9386418940884026,
|
402 |
+
"precision": 0.9392845859659347,
|
403 |
+
"recall": 0.9383283582089552,
|
404 |
+
"support": 33500.0
|
405 |
},
|
406 |
"step": 810
|
407 |
},
|
408 |
{
|
409 |
"epoch": 11.0,
|
410 |
"eval_B": {
|
411 |
+
"f1-score": 0.8901136755080951,
|
412 |
+
"precision": 0.8831168831168831,
|
413 |
+
"recall": 0.8972222222222223,
|
414 |
+
"support": 1440.0
|
415 |
},
|
416 |
"eval_I": {
|
417 |
+
"f1-score": 0.9620073001078947,
|
418 |
+
"precision": 0.9535359970874671,
|
419 |
+
"recall": 0.9706304720433594,
|
420 |
+
"support": 21587.0
|
421 |
},
|
422 |
"eval_O": {
|
423 |
+
"f1-score": 0.917413322945072,
|
424 |
+
"precision": 0.9361025539103647,
|
425 |
+
"recall": 0.8994557433400172,
|
426 |
+
"support": 10473.0
|
427 |
},
|
428 |
+
"eval_accuracy": 0.9452238805970149,
|
429 |
+
"eval_loss": 0.3123624622821808,
|
430 |
"eval_macro avg": {
|
431 |
+
"f1-score": 0.9231780995203539,
|
432 |
+
"precision": 0.9242518113715716,
|
433 |
+
"recall": 0.922436145868533,
|
434 |
+
"support": 33500.0
|
435 |
+
},
|
436 |
+
"eval_runtime": 4.7539,
|
437 |
+
"eval_samples_per_second": 17.039,
|
438 |
+
"eval_steps_per_second": 2.314,
|
439 |
"eval_weighted avg": {
|
440 |
+
"f1-score": 0.9449756719810304,
|
441 |
+
"precision": 0.9450588635199616,
|
442 |
+
"recall": 0.9452238805970149,
|
443 |
+
"support": 33500.0
|
444 |
},
|
445 |
"step": 891
|
446 |
},
|
447 |
{
|
448 |
"epoch": 12.0,
|
449 |
"eval_B": {
|
450 |
+
"f1-score": 0.8800819952169457,
|
451 |
+
"precision": 0.8661735036987223,
|
452 |
+
"recall": 0.8944444444444445,
|
453 |
+
"support": 1440.0
|
454 |
},
|
455 |
"eval_I": {
|
456 |
+
"f1-score": 0.9595463311598861,
|
457 |
+
"precision": 0.9512039692293687,
|
458 |
+
"recall": 0.9680363181544448,
|
459 |
+
"support": 21587.0
|
460 |
},
|
461 |
"eval_O": {
|
462 |
+
"f1-score": 0.9115367743822197,
|
463 |
+
"precision": 0.9310035842293907,
|
464 |
+
"recall": 0.8928673732454884,
|
465 |
+
"support": 10473.0
|
466 |
},
|
467 |
+
"eval_accuracy": 0.9413731343283582,
|
468 |
+
"eval_loss": 0.3427491784095764,
|
469 |
"eval_macro avg": {
|
470 |
+
"f1-score": 0.9170550335863505,
|
471 |
+
"precision": 0.9161270190524938,
|
472 |
+
"recall": 0.9184493786147926,
|
473 |
+
"support": 33500.0
|
474 |
+
},
|
475 |
+
"eval_runtime": 4.7455,
|
476 |
+
"eval_samples_per_second": 17.069,
|
477 |
+
"eval_steps_per_second": 2.318,
|
478 |
"eval_weighted avg": {
|
479 |
+
"f1-score": 0.9411214734915179,
|
480 |
+
"precision": 0.9412337452750731,
|
481 |
+
"recall": 0.9413731343283582,
|
482 |
+
"support": 33500.0
|
483 |
},
|
484 |
"step": 972
|
485 |
},
|
486 |
{
|
487 |
"epoch": 12.35,
|
488 |
+
"grad_norm": 0.47551417350769043,
|
489 |
"learning_rate": 1.506172839506173e-05,
|
490 |
+
"loss": 0.0222,
|
491 |
"step": 1000
|
492 |
},
|
493 |
{
|
494 |
"epoch": 13.0,
|
495 |
"eval_B": {
|
496 |
+
"f1-score": 0.8896434634974534,
|
497 |
+
"precision": 0.8704318936877077,
|
498 |
+
"recall": 0.9097222222222222,
|
499 |
+
"support": 1440.0
|
500 |
},
|
501 |
"eval_I": {
|
502 |
+
"f1-score": 0.9620136667970457,
|
503 |
+
"precision": 0.9556591698665204,
|
504 |
+
"recall": 0.9684532357437347,
|
505 |
+
"support": 21587.0
|
506 |
},
|
507 |
"eval_O": {
|
508 |
+
"f1-score": 0.9183177933177933,
|
509 |
+
"precision": 0.9343808676746714,
|
510 |
+
"recall": 0.9027976701995608,
|
511 |
+
"support": 10473.0
|
512 |
},
|
513 |
+
"eval_accuracy": 0.9454029850746268,
|
514 |
+
"eval_loss": 0.3816670775413513,
|
515 |
"eval_macro avg": {
|
516 |
+
"f1-score": 0.9233249745374308,
|
517 |
+
"precision": 0.9201573104096331,
|
518 |
+
"recall": 0.9269910427218392,
|
519 |
+
"support": 33500.0
|
520 |
+
},
|
521 |
+
"eval_runtime": 4.7247,
|
522 |
+
"eval_samples_per_second": 17.144,
|
523 |
+
"eval_steps_per_second": 2.328,
|
524 |
"eval_weighted avg": {
|
525 |
+
"f1-score": 0.945242324238848,
|
526 |
+
"precision": 0.9453435001186778,
|
527 |
+
"recall": 0.9454029850746268,
|
528 |
+
"support": 33500.0
|
529 |
},
|
530 |
"step": 1053
|
531 |
},
|
532 |
{
|
533 |
"epoch": 14.0,
|
534 |
"eval_B": {
|
535 |
+
"f1-score": 0.8865272540281112,
|
536 |
+
"precision": 0.8754231550440081,
|
537 |
+
"recall": 0.8979166666666667,
|
538 |
+
"support": 1440.0
|
539 |
},
|
540 |
"eval_I": {
|
541 |
+
"f1-score": 0.9599206715247671,
|
542 |
+
"precision": 0.9557331129172981,
|
543 |
+
"recall": 0.9641450873210728,
|
544 |
+
"support": 21587.0
|
545 |
},
|
546 |
"eval_O": {
|
547 |
+
"f1-score": 0.9141367826632559,
|
548 |
+
"precision": 0.9242631270739801,
|
549 |
+
"recall": 0.9042299245679366,
|
550 |
+
"support": 10473.0
|
551 |
},
|
552 |
+
"eval_accuracy": 0.9425671641791045,
|
553 |
+
"eval_loss": 0.3827010989189148,
|
554 |
"eval_macro avg": {
|
555 |
+
"f1-score": 0.9201949027387114,
|
556 |
+
"precision": 0.9184731316784287,
|
557 |
+
"recall": 0.9220972261852255,
|
558 |
+
"support": 33500.0
|
559 |
+
},
|
560 |
+
"eval_runtime": 4.7319,
|
561 |
+
"eval_samples_per_second": 17.118,
|
562 |
+
"eval_steps_per_second": 2.325,
|
563 |
"eval_weighted avg": {
|
564 |
+
"f1-score": 0.9424525763235196,
|
565 |
+
"precision": 0.9424426203479068,
|
566 |
+
"recall": 0.9425671641791045,
|
567 |
+
"support": 33500.0
|
568 |
},
|
569 |
"step": 1134
|
570 |
}
|
|
|
574 |
"num_input_tokens_seen": 0,
|
575 |
"num_train_epochs": 50,
|
576 |
"save_steps": 500,
|
577 |
+
"total_flos": 2006761544701200.0,
|
578 |
"train_batch_size": 4,
|
579 |
"trial_name": null,
|
580 |
"trial_params": null
|
checkpoint-1134/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8ca363922308e3892528dd031742ffedc372734b464a042d09444af9700901e
|
3 |
size 4856
|